--- zzzz-none-000/linux-3.10.107/arch/powerpc/kernel/nvram_64.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/powerpc/kernel/nvram_64.c 2021-02-04 17:41:59.000000000 +0000 @@ -26,6 +26,9 @@ #include #include #include +#include +#include +#include #include #include #include @@ -54,6 +57,680 @@ static LIST_HEAD(nvram_partitions); +#ifdef CONFIG_PPC_PSERIES +struct nvram_os_partition rtas_log_partition = { + .name = "ibm,rtas-log", + .req_size = 2079, + .min_size = 1055, + .index = -1, + .os_partition = true +}; +#endif + +struct nvram_os_partition oops_log_partition = { + .name = "lnx,oops-log", + .req_size = 4000, + .min_size = 2000, + .index = -1, + .os_partition = true +}; + +static const char *nvram_os_partitions[] = { +#ifdef CONFIG_PPC_PSERIES + "ibm,rtas-log", +#endif + "lnx,oops-log", + NULL +}; + +static void oops_to_nvram(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason); + +static struct kmsg_dumper nvram_kmsg_dumper = { + .dump = oops_to_nvram +}; + +/* + * For capturing and compressing an oops or panic report... + + * big_oops_buf[] holds the uncompressed text we're capturing. + * + * oops_buf[] holds the compressed text, preceded by a oops header. + * oops header has u16 holding the version of oops header (to differentiate + * between old and new format header) followed by u16 holding the length of + * the compressed* text (*Or uncompressed, if compression fails.) and u64 + * holding the timestamp. oops_buf[] gets written to NVRAM. + * + * oops_log_info points to the header. oops_data points to the compressed text. + * + * +- oops_buf + * | +- oops_data + * v v + * +-----------+-----------+-----------+------------------------+ + * | version | length | timestamp | text | + * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) | + * +-----------+-----------+-----------+------------------------+ + * ^ + * +- oops_log_info + * + * We preallocate these buffers during init to avoid kmalloc during oops/panic. + */ +static size_t big_oops_buf_sz; +static char *big_oops_buf, *oops_buf; +static char *oops_data; +static size_t oops_data_sz; + +/* Compression parameters */ +#define COMPR_LEVEL 6 +#define WINDOW_BITS 12 +#define MEM_LEVEL 4 +static struct z_stream_s stream; + +#ifdef CONFIG_PSTORE +#ifdef CONFIG_PPC_POWERNV +static struct nvram_os_partition skiboot_partition = { + .name = "ibm,skiboot", + .index = -1, + .os_partition = false +}; +#endif + +#ifdef CONFIG_PPC_PSERIES +static struct nvram_os_partition of_config_partition = { + .name = "of-config", + .index = -1, + .os_partition = false +}; +#endif + +static struct nvram_os_partition common_partition = { + .name = "common", + .index = -1, + .os_partition = false +}; + +static enum pstore_type_id nvram_type_ids[] = { + PSTORE_TYPE_DMESG, + PSTORE_TYPE_PPC_COMMON, + -1, + -1, + -1 +}; +static int read_type; +#endif + +/* nvram_write_os_partition + * + * We need to buffer the error logs into nvram to ensure that we have + * the failure information to decode. If we have a severe error there + * is no way to guarantee that the OS or the machine is in a state to + * get back to user land and write the error to disk. For example if + * the SCSI device driver causes a Machine Check by writing to a bad + * IO address, there is no way of guaranteeing that the device driver + * is in any state that is would also be able to write the error data + * captured to disk, thus we buffer it in NVRAM for analysis on the + * next boot. + * + * In NVRAM the partition containing the error log buffer will looks like: + * Header (in bytes): + * +-----------+----------+--------+------------+------------------+ + * | signature | checksum | length | name | data | + * |0 |1 |2 3|4 15|16 length-1| + * +-----------+----------+--------+------------+------------------+ + * + * The 'data' section would look like (in bytes): + * +--------------+------------+-----------------------------------+ + * | event_logged | sequence # | error log | + * |0 3|4 7|8 error_log_size-1| + * +--------------+------------+-----------------------------------+ + * + * event_logged: 0 if event has not been logged to syslog, 1 if it has + * sequence #: The unique sequence # for each event. (until it wraps) + * error log: The error log from event_scan + */ +int nvram_write_os_partition(struct nvram_os_partition *part, + char *buff, int length, + unsigned int err_type, + unsigned int error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (part->index == -1) + return -ESPIPE; + + if (length > part->size) + length = part->size; + + info.error_type = cpu_to_be32(err_type); + info.seq_num = cpu_to_be32(error_log_cnt); + + tmp_index = part->index; + + rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), + &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); + return rc; + } + + rc = ppc_md.nvram_write(buff, length, &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); + return rc; + } + + return 0; +} + +/* nvram_read_partition + * + * Reads nvram partition for at most 'length' + */ +int nvram_read_partition(struct nvram_os_partition *part, char *buff, + int length, unsigned int *err_type, + unsigned int *error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (part->index == -1) + return -1; + + if (length > part->size) + length = part->size; + + tmp_index = part->index; + + if (part->os_partition) { + rc = ppc_md.nvram_read((char *)&info, + sizeof(struct err_log_info), + &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); + return rc; + } + } + + rc = ppc_md.nvram_read(buff, length, &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); + return rc; + } + + if (part->os_partition) { + *error_log_cnt = be32_to_cpu(info.seq_num); + *err_type = be32_to_cpu(info.error_type); + } + + return 0; +} + +/* nvram_init_os_partition + * + * This sets up a partition with an "OS" signature. + * + * The general strategy is the following: + * 1.) If a partition with the indicated name already exists... + * - If it's large enough, use it. + * - Otherwise, recycle it and keep going. + * 2.) Search for a free partition that is large enough. + * 3.) If there's not a free partition large enough, recycle any obsolete + * OS partitions and try again. + * 4.) Will first try getting a chunk that will satisfy the requested size. + * 5.) If a chunk of the requested size cannot be allocated, then try finding + * a chunk that will satisfy the minum needed. + * + * Returns 0 on success, else -1. + */ +int __init nvram_init_os_partition(struct nvram_os_partition *part) +{ + loff_t p; + int size; + + /* Look for ours */ + p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); + + /* Found one but too small, remove it */ + if (p && size < part->min_size) { + pr_info("nvram: Found too small %s partition," + " removing it...\n", part->name); + nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL); + p = 0; + } + + /* Create one if we didn't find */ + if (!p) { + p = nvram_create_partition(part->name, NVRAM_SIG_OS, + part->req_size, part->min_size); + if (p == -ENOSPC) { + pr_info("nvram: No room to create %s partition, " + "deleting any obsolete OS partitions...\n", + part->name); + nvram_remove_partition(NULL, NVRAM_SIG_OS, + nvram_os_partitions); + p = nvram_create_partition(part->name, NVRAM_SIG_OS, + part->req_size, part->min_size); + } + } + + if (p <= 0) { + pr_err("nvram: Failed to find or create %s" + " partition, err %d\n", part->name, (int)p); + return -1; + } + + part->index = p; + part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info); + + return 0; +} + +/* Derived from logfs_compress() */ +static int nvram_compress(const void *in, void *out, size_t inlen, + size_t outlen) +{ + int err, ret; + + ret = -EIO; + err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS, + MEM_LEVEL, Z_DEFAULT_STRATEGY); + if (err != Z_OK) + goto error; + + stream.next_in = in; + stream.avail_in = inlen; + stream.total_in = 0; + stream.next_out = out; + stream.avail_out = outlen; + stream.total_out = 0; + + err = zlib_deflate(&stream, Z_FINISH); + if (err != Z_STREAM_END) + goto error; + + err = zlib_deflateEnd(&stream); + if (err != Z_OK) + goto error; + + if (stream.total_out >= stream.total_in) + goto error; + + ret = stream.total_out; +error: + return ret; +} + +/* Compress the text from big_oops_buf into oops_buf. */ +static int zip_oops(size_t text_len) +{ + struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; + int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len, + oops_data_sz); + if (zipped_len < 0) { + pr_err("nvram: compression failed; returned %d\n", zipped_len); + pr_err("nvram: logging uncompressed oops/panic report\n"); + return -1; + } + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(zipped_len); + oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds()); + return 0; +} + +#ifdef CONFIG_PSTORE +static int nvram_pstore_open(struct pstore_info *psi) +{ + /* Reset the iterator to start reading partitions again */ + read_type = -1; + return 0; +} + +/** + * nvram_pstore_write - pstore write callback for nvram + * @type: Type of message logged + * @reason: reason behind dump (oops/panic) + * @id: identifier to indicate the write performed + * @part: pstore writes data to registered buffer in parts, + * part number will indicate the same. + * @count: Indicates oops count + * @compressed: Flag to indicate the log is compressed + * @size: number of bytes written to the registered buffer + * @psi: registered pstore_info structure + * + * Called by pstore_dump() when an oops or panic report is logged in the + * printk buffer. + * Returns 0 on successful write. + */ +static int nvram_pstore_write(enum pstore_type_id type, + enum kmsg_dump_reason reason, + u64 *id, unsigned int part, int count, + bool compressed, size_t size, + struct pstore_info *psi) +{ + int rc; + unsigned int err_type = ERR_TYPE_KERNEL_PANIC; + struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf; + + /* part 1 has the recent messages from printk buffer */ + if (part > 1 || (type != PSTORE_TYPE_DMESG)) + return -1; + + if (clobbering_unread_rtas_event()) + return -1; + + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(size); + oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds()); + + if (compressed) + err_type = ERR_TYPE_KERNEL_PANIC_GZ; + + rc = nvram_write_os_partition(&oops_log_partition, oops_buf, + (int) (sizeof(*oops_hdr) + size), err_type, count); + + if (rc != 0) + return rc; + + *id = part; + return 0; +} + +/* + * Reads the oops/panic report, rtas, of-config and common partition. + * Returns the length of the data we read from each partition. + * Returns 0 if we've been called before. + */ +static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, + int *count, struct timespec *time, char **buf, + bool *compressed, struct pstore_info *psi) +{ + struct oops_log_info *oops_hdr; + unsigned int err_type, id_no, size = 0; + struct nvram_os_partition *part = NULL; + char *buff = NULL; + int sig = 0; + loff_t p; + + read_type++; + + switch (nvram_type_ids[read_type]) { + case PSTORE_TYPE_DMESG: + part = &oops_log_partition; + *type = PSTORE_TYPE_DMESG; + break; + case PSTORE_TYPE_PPC_COMMON: + sig = NVRAM_SIG_SYS; + part = &common_partition; + *type = PSTORE_TYPE_PPC_COMMON; + *id = PSTORE_TYPE_PPC_COMMON; + time->tv_sec = 0; + time->tv_nsec = 0; + break; +#ifdef CONFIG_PPC_PSERIES + case PSTORE_TYPE_PPC_RTAS: + part = &rtas_log_partition; + *type = PSTORE_TYPE_PPC_RTAS; + time->tv_sec = last_rtas_event; + time->tv_nsec = 0; + break; + case PSTORE_TYPE_PPC_OF: + sig = NVRAM_SIG_OF; + part = &of_config_partition; + *type = PSTORE_TYPE_PPC_OF; + *id = PSTORE_TYPE_PPC_OF; + time->tv_sec = 0; + time->tv_nsec = 0; + break; +#endif +#ifdef CONFIG_PPC_POWERNV + case PSTORE_TYPE_PPC_OPAL: + sig = NVRAM_SIG_FW; + part = &skiboot_partition; + *type = PSTORE_TYPE_PPC_OPAL; + *id = PSTORE_TYPE_PPC_OPAL; + time->tv_sec = 0; + time->tv_nsec = 0; + break; +#endif + default: + return 0; + } + + if (!part->os_partition) { + p = nvram_find_partition(part->name, sig, &size); + if (p <= 0) { + pr_err("nvram: Failed to find partition %s, " + "err %d\n", part->name, (int)p); + return 0; + } + part->index = p; + part->size = size; + } + + buff = kmalloc(part->size, GFP_KERNEL); + + if (!buff) + return -ENOMEM; + + if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) { + kfree(buff); + return 0; + } + + *count = 0; + + if (part->os_partition) + *id = id_no; + + if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { + size_t length, hdr_size; + + oops_hdr = (struct oops_log_info *)buff; + if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { + /* Old format oops header had 2-byte record size */ + hdr_size = sizeof(u16); + length = be16_to_cpu(oops_hdr->version); + time->tv_sec = 0; + time->tv_nsec = 0; + } else { + hdr_size = sizeof(*oops_hdr); + length = be16_to_cpu(oops_hdr->report_length); + time->tv_sec = be64_to_cpu(oops_hdr->timestamp); + time->tv_nsec = 0; + } + *buf = kmemdup(buff + hdr_size, length, GFP_KERNEL); + if (*buf == NULL) + return -ENOMEM; + kfree(buff); + + if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) + *compressed = true; + else + *compressed = false; + return length; + } + + *buf = buff; + return part->size; +} + +static struct pstore_info nvram_pstore_info = { + .owner = THIS_MODULE, + .name = "nvram", + .open = nvram_pstore_open, + .read = nvram_pstore_read, + .write = nvram_pstore_write, +}; + +static int nvram_pstore_init(void) +{ + int rc = 0; + + if (machine_is(pseries)) { + nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS; + nvram_type_ids[3] = PSTORE_TYPE_PPC_OF; + } else + nvram_type_ids[2] = PSTORE_TYPE_PPC_OPAL; + + nvram_pstore_info.buf = oops_data; + nvram_pstore_info.bufsize = oops_data_sz; + + spin_lock_init(&nvram_pstore_info.buf_lock); + + rc = pstore_register(&nvram_pstore_info); + if (rc && (rc != -EPERM)) + /* Print error only when pstore.backend == nvram */ + pr_err("nvram: pstore_register() failed, returned %d. " + "Defaults to kmsg_dump\n", rc); + + return rc; +} +#else +static int nvram_pstore_init(void) +{ + return -1; +} +#endif + +void __init nvram_init_oops_partition(int rtas_partition_exists) +{ + int rc; + + rc = nvram_init_os_partition(&oops_log_partition); + if (rc != 0) { +#ifdef CONFIG_PPC_PSERIES + if (!rtas_partition_exists) { + pr_err("nvram: Failed to initialize oops partition!"); + return; + } + pr_notice("nvram: Using %s partition to log both" + " RTAS errors and oops/panic reports\n", + rtas_log_partition.name); + memcpy(&oops_log_partition, &rtas_log_partition, + sizeof(rtas_log_partition)); +#else + pr_err("nvram: Failed to initialize oops partition!"); + return; +#endif + } + oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL); + if (!oops_buf) { + pr_err("nvram: No memory for %s partition\n", + oops_log_partition.name); + return; + } + oops_data = oops_buf + sizeof(struct oops_log_info); + oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); + + rc = nvram_pstore_init(); + + if (!rc) + return; + + /* + * Figure compression (preceded by elimination of each line's + * severity prefix) will reduce the oops/panic report to at most + * 45% of its original size. + */ + big_oops_buf_sz = (oops_data_sz * 100) / 45; + big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); + if (big_oops_buf) { + stream.workspace = kmalloc(zlib_deflate_workspacesize( + WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); + if (!stream.workspace) { + pr_err("nvram: No memory for compression workspace; " + "skipping compression of %s partition data\n", + oops_log_partition.name); + kfree(big_oops_buf); + big_oops_buf = NULL; + } + } else { + pr_err("No memory for uncompressed %s data; " + "skipping compression\n", oops_log_partition.name); + stream.workspace = NULL; + } + + rc = kmsg_dump_register(&nvram_kmsg_dumper); + if (rc != 0) { + pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); + kfree(oops_buf); + kfree(big_oops_buf); + kfree(stream.workspace); + } +} + +/* + * This is our kmsg_dump callback, called after an oops or panic report + * has been written to the printk buffer. We want to capture as much + * of the printk buffer as possible. First, capture as much as we can + * that we think will compress sufficiently to fit in the lnx,oops-log + * partition. If that's too much, go back and capture uncompressed text. + */ +static void oops_to_nvram(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; + static unsigned int oops_count = 0; + static bool panicking = false; + static DEFINE_SPINLOCK(lock); + unsigned long flags; + size_t text_len; + unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; + int rc = -1; + + switch (reason) { + case KMSG_DUMP_RESTART: + case KMSG_DUMP_HALT: + case KMSG_DUMP_POWEROFF: + /* These are almost always orderly shutdowns. */ + return; + case KMSG_DUMP_OOPS: + break; + case KMSG_DUMP_PANIC: + panicking = true; + break; + case KMSG_DUMP_EMERG: + if (panicking) + /* Panic report already captured. */ + return; + break; + default: + pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", + __func__, (int) reason); + return; + } + + if (clobbering_unread_rtas_event()) + return; + + if (!spin_trylock_irqsave(&lock, flags)) + return; + + if (big_oops_buf) { + kmsg_dump_get_buffer(dumper, false, + big_oops_buf, big_oops_buf_sz, &text_len); + rc = zip_oops(text_len); + } + if (rc != 0) { + kmsg_dump_rewind(dumper); + kmsg_dump_get_buffer(dumper, false, + oops_data, oops_data_sz, &text_len); + err_type = ERR_TYPE_KERNEL_PANIC; + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(text_len); + oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds()); + } + + (void) nvram_write_os_partition(&oops_log_partition, oops_buf, + (int) (sizeof(*oops_hdr) + text_len), err_type, + ++oops_count); + + spin_unlock_irqrestore(&lock, flags); +} + static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin) { int size; @@ -84,22 +761,30 @@ char *tmp = NULL; ssize_t size; - ret = -ENODEV; - if (!ppc_md.nvram_size) + if (!ppc_md.nvram_size) { + ret = -ENODEV; goto out; + } - ret = 0; size = ppc_md.nvram_size(); - if (*ppos >= size || size < 0) + if (size < 0) { + ret = size; goto out; + } + + if (*ppos >= size) { + ret = 0; + goto out; + } count = min_t(size_t, count, size - *ppos); count = min(count, PAGE_SIZE); - ret = -ENOMEM; tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) + if (!tmp) { + ret = -ENOMEM; goto out; + } ret = ppc_md.nvram_read(tmp, count, ppos); if (ret <= 0) @@ -202,7 +887,7 @@ printk(KERN_WARNING "--------%s---------\n", label); printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n"); list_for_each_entry(tmp_part, &nvram_partitions, partition) { - printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%12s\n", + printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%12.12s\n", tmp_part->index, tmp_part->header.signature, tmp_part->header.checksum, tmp_part->header.length, tmp_part->header.name); @@ -215,9 +900,13 @@ { loff_t tmp_index; int rc; - + struct nvram_header phead; + + memcpy(&phead, &part->header, NVRAM_HEADER_LEN); + phead.length = cpu_to_be16(phead.length); + tmp_index = part->index; - rc = ppc_md.nvram_write((char *)&part->header, NVRAM_HEADER_LEN, &tmp_index); + rc = ppc_md.nvram_write((char *)&phead, NVRAM_HEADER_LEN, &tmp_index); return rc; } @@ -376,7 +1065,7 @@ /* Create our OS partition */ new_part = kmalloc(sizeof(*new_part), GFP_KERNEL); if (!new_part) { - pr_err("nvram_create_os_partition: kmalloc failed\n"); + pr_err("%s: kmalloc failed\n", __func__); return -ENOMEM; } @@ -388,8 +1077,8 @@ rc = nvram_write_header(new_part); if (rc <= 0) { - pr_err("nvram_create_os_partition: nvram_write_header " - "failed (%d)\n", rc); + pr_err("%s: nvram_write_header failed (%d)\n", __func__, rc); + kfree(new_part); return rc; } list_add_tail(&new_part->partition, &free_part->partition); @@ -401,8 +1090,8 @@ free_part->header.checksum = nvram_checksum(&free_part->header); rc = nvram_write_header(free_part); if (rc <= 0) { - pr_err("nvram_create_os_partition: nvram_write_header " - "failed (%d)\n", rc); + pr_err("%s: nvram_write_header failed (%d)\n", + __func__, rc); return rc; } } else { @@ -416,11 +1105,12 @@ tmp_index += NVRAM_BLOCK_LEN) { rc = ppc_md.nvram_write(nv_init_vals, NVRAM_BLOCK_LEN, &tmp_index); if (rc <= 0) { - pr_err("nvram_create_partition: nvram_write failed (%d)\n", rc); + pr_err("%s: nvram_write failed (%d)\n", + __func__, rc); return rc; } } - + return new_part->index + NVRAM_HEADER_LEN; } @@ -497,6 +1187,8 @@ memcpy(&phead, header, NVRAM_HEADER_LEN); + phead.length = be16_to_cpu(phead.length); + err = 0; c_sum = nvram_checksum(&phead); if (c_sum != phead.checksum) { @@ -553,7 +1245,7 @@ return rc; } -void __exit nvram_cleanup(void) +static void __exit nvram_cleanup(void) { misc_deregister( &nvram_dev ); }